Abstract: Direct injection of a data to be transferred in a hybrid computing environment that includes a host computer and a plurality of accelerators, the host computer and the accelerators adapted to one another for data communications by a system level message passing module. Each accelerator includes a Power Processing Element (‘PPE’) and a plurality of Synergistic Processing Elements (‘SPEs’). Direct injection includes reserving, by each SPE, a slot in a shared memory region accessible by the host computer; loading, by each SPE into local memory of the SPE, a portion of data to be transferred to the host computer; executing, by each SPE in parallel, a data processing operation on the portion of the data loaded in local memory of each SPE; and writing, by each SPE, the processed data to the SPE's reserved slot in the shared memory region accessible by the host computer.

Abstract: Direct injection of a data to be transferred in a hybrid computing environment that includes a host computer and a plurality of accelerators, the host computer and the accelerators adapted to one another for data communications by a system level message passing module. Each accelerator includes a Power Processing Element (‘PPE’) and a plurality of Synergistic Processing Elements (‘SPEs’). Direct injection includes reserving, by each SPE, a slot in a shared memory region accessible by the host computer; loading, by each SPE into local memory of the SPE, a portion of data to be transferred to the host computer; executing, by each SPE in parallel, a data processing operation on the portion of the data loaded in local memory of each SPE; and writing, by each SPE, the processed data to the SPE's reserved slot in the shared memory region accessible by the host computer.

Abstract: A circuit arrangement, program product and method stream level of detail components between hardware threads in a multithreaded circuit arrangement to perform physics collision detection. Typically, a master hardware thread, e.g., a component loader hardware thread, is used to retrieve level of detail data for an object from a memory and stream the data to one or more slave hardware threads, e.g., collision detection hardware threads, to perform the actual collision detection. Because the slave hardware threads receive the level of detail data from the master thread, typically the slave hardware threads are not required to load the data from the memory, thereby reducing memory bandwidth requirements and accelerating performance.

Abstract: Embodiments of the invention intelligently associate processes with core processors in a multi-core processor. The core processors are asymmetrical in that the core processors support different features or provide different resources. The features or resources are published by the core processors or otherwise identified (e.g., via a query). Responsive to a request to execute an instruction associated with a thread, one of the core processors is selected based on the resource or feature supporting execution of the instruction. The thread is assigned to the selected core processor such that the selected core processor executes the instruction and subsequent instructions from the assigned thread. In some embodiments, the resource or feature is emulated until an activity limit is reached upon which the thread assignment occurs.

Abstract: Disclosed herein are lattice reduction systems and methods for a MIMO communication system. One such method includes providing a channel matrix corresponding to a channel in a MIMO communication system, preprocessing the channel matrix to form at least an upper triangular matrix, implementing a relaxed size reduction process, and implementing a basis update process. Implementing the relaxed size reduction process comprises choosing a first relaxed size reduction parameter for a first-off-diagonal element of the upper triangular matrix, choosing a second relaxed size reduction parameter, which is greater than the first relaxed size reduction parameter, for a second-off-diagonal element of the upper triangular matrix evaluating whether a first relaxed size reduction condition is satisfied for the first-off-diagonal element of the upper triangular matrix, and evaluating whether a second relaxed size reduction condition is satisfied for the second-off-diagonal element of the upper triangular matrix.

Abstract: A method and apparatus for resource management in a multicore processor is disclosed. A system management controller (130) provides omnipresent scheduling, synchronization, load balancing, and power and memory management services to each processing resource (150) within in a multicore processor (10), via a plurality of system management clients (120) implemented in hardware or software. The controller (130) allocates the tasks executing in each processing resource (150) by means of interrupt control signals, which interact directly with the system management clients (120), enabling processing resources (150) to autonomously create, execute and distribute tasks around a parallel system architecture whilst monitoring and policing the use of shared system resources (140).

Abstract: A multiprocessor system includes a master processor, at least one slave processor, and a synchronization unit. The master processor has a first flag indicating whether the master processor is in a task activation accepting state and a second flag reflective of a flag of a slave processor, iteratively updates the first flag at a frequency based on the volume of tasks processed by the master processor, and activates a task on the master processor or the slave processor based on the first flag and the second flag. Each slave processor has a third flag indicating whether the slave processor is in the task activation accepting state and iteratively updates the third flag at a frequency based on the volume of tasks processed by the slave processor. Tasks are allocated to the slave processor by the master processor. The synchronization unit synchronizes the third flag and the second flag.

Abstract: Techniques are provided for dynamically re-ordering operation requests that have previously been submitted to a queue management unit. After the queue management unit has placed multiple requests in a queue to be executed in an order that is based on priorities that were assigned to the operations, the entity that requested the operations (the “requester”) sends one or more priority-change messages. The one or more priority-change messages include requests to perform operations that have already been queued. For at least one of the operations, the priority assigned to the operation in the subsequent request is different from the priority that was assigned to the same operation when that operation was initially queued for execution. Based on the change in priority, the operation whose priority has change is placed at a different location in the queue, relative to the other operations in the queue that were requested by the same requester.

Abstract: A scheduler receives at least one flexible reservation request for scheduling in a computing environment comprising consumable resources. The flexible reservation request specifies a duration and at least one required resource. The consumable resources comprise at least one machine resource and at least one floating resource. The scheduler creates a flexible job for the at least one flexible reservation request and places the flexible job in a prioritized job queue for scheduling, wherein the flexible job is prioritizes relative to at least one regular job in the prioritized job queue. The scheduler adds a reservation set to a waiting state for the at least one flexible reservation request.

Abstract: An information processing device which has a plurality of process units for performing various kinds of processes includes a detecting unit that detects a processing loads of the process units; a determining unit that determines whether a total amount of the processing loads detected by the detecting unit is equal to or larger than a specific value; a designating unit that designates a process unit having a process state to be controlled, based on the processing loads of the process units detected by the detecting unit, when the determining unit determines that the total amount is equal to or larger than the specific value; a process identifying unit that identifies a process having an execution state to be controlled among processes being performed by the process unit designated by the designating unit; and a control unit that controls the execution state of the process identified by the process identifying unit.

Abstract: A microprocessor integrated circuit includes first and second processors, an internal memory accessible by the first and second processors, and a bus interface unit configured to interface to a bus external to the microprocessor for providing access to a memory external to the microprocessor. The bus interface unit, external bus, and external memory are accessible by the second processor but are inaccessible by the first processor. The first processor writes debug information to the internal memory. The first processor detects an event and provides a notification of the event to the second processor. The second processor, coupled to the bus interface unit, executes microcode in response to the event notification received from the first processor. The microcode reads the debug information from the internal memory and writes the debug information to the external memory via the bus interface unit and external bus for use in debugging the second processor.

Abstract: Systems and methods are provided for a core management system for parallel processing of an evolutionary algorithm.

Abstract: Executing an accelerator application program in a hybrid computing environment with a host computer having a host computer architecture; an accelerator having an accelerator architecture, the accelerator architecture optimized, with respect to the host computer architecture, for speed of execution of a particular class of computing functions; the host computer and the accelerator adapted to one another for data communications by a system level message passing module, where executing an accelerator application program on an accelerator includes receiving, from a host application program on the host computer, operating information for an accelerator application program; designating a directory as a CWD for the accelerator application program, separate from any other CWDs of any other applications running on the accelerator; assigning, to the CWD, a name that is unique with respect to names of other CWDs of other applications in the computing environment; and starting the accelerator application program on the a

Abstract: An electronic system includes a master module having a first control unit having one or more first serial interfaces and being programmed to output a first data signal and a first clock signal through the one or more first serial interfaces, and a slave module having a second control unit, the second control unit having a second serial interface. The slave module receives the first clock signal through the second serial interface, and the second control unit is programmed to monitor the slave module for a fault condition and output a second clock signal through the second serial interface which is (i) the same as the first clock signal if a fault condition on the slave module is not detected, and (ii) a modified clock signal having a predetermined format through the second serial interface if a fault condition on the slave module is detected.

Abstract: A computing system has a stack of microprocessor chips that are designed to work together in a multiprocessor system. The chips are interconnected with 3D through vias, or alternatively by compatible package carriers having the interconnections, while logically the chips in the stack are interconnected via specialized cache coherent interconnections. All of the chips in the stack use the same logical chip design, even though they can be easily personalized by setting specialized latches on the chips. One or more of the individual microprocessor chips utilized in the stack are implemented in a silicon process that is optimized for high performance while others are implemented in a silicon process that is optimized for power consumption i.e. for the best performance per Watt of electrical power consumed. The hypervisor or operating system controls the utilization of individual chips of a stack.

Abstract: Dynamically managing a thread pool associated with a plurality of sub-applications. A request for at least one of the sub-applications is received. A quantity of threads currently assigned to the at least one of the sub-applications is determined. The determined quantity of threads is compared to a predefined maximum thread threshold. A thread in the thread pool is assigned to handle the received request if the determined quantity of threads is not greater than the predefined maximum thread threshold. Embodiments enable control of the quantity of threads within the thread pool assigned to each of the sub-applications. Further embodiments manage the threads for the sub-applications based on latency of the sub-applications.

Abstract: A Method to redirect SRB routines from otherwise non-zIIP eligible processes on an IBM z/OS series mainframe to a zIIP eligible enclave is disclosed. This redirection is achieved by intercepting otherwise blocked operations and allowing them to complete processing without errors imposed by the zIIP processor configuration. After appropriately intercepting and redirecting these blocked operations more processing may be performed on the more financially cost effective zIIP processor by users of mainframe computing environments.

Abstract: A Method to redirect SRB routines from otherwise non-zIIP eligible processes on an IBM z/OS series mainframe to a zIIP eligible enclave is disclosed. This redirection is achieved by intercepting otherwise blocked operations and allowing them to complete processing without errors imposed by the zIIP processor configuration. After appropriately intercepting and redirecting these blocked operations more processing may be performed on the more financially cost effective zIIP processor by users of mainframe computing environments.

Abstract: A wireless communication base station comprising a plurality of application specific instruction set processors (ASISPs) configured to support one or more processes hosted by the base station, and to track process state information associated with each of the processes; and a memory configured to store the tracked process state information, and when an ASISP of the plurality of ASISPs is reallocated from a first process to a second process, the respective ASISP is configured to retrieve from the memory process state information for the second process.

Abstract: In one embodiment of the present invention, a method includes verifying a master processor of a system; validating a trusted agent with the master processor if the master processor is verified; and launching the trusted agent on a plurality of processors of the system if the trusted agent is validated. After execution of such a trusted agent, a secure kernel may then be launched, in certain embodiments. The system may be a multiprocessor server system having a partially or fully connected topology with arbitrary point-to-point interconnects, for example.

Abstract: The invention provides a topology collection method and dual control board device applicable to a stacking system comprising dual control board devices. A master control board of a dual control board device advertises through a stack port the topology information of the member device in which the master control board resides, including information about the master control board and, if a slave control board is present, information about the slave control board; and stores the topology information or updates the existing topology information upon receiving the topology information of the stacking system through the stack port, and backs up the stored topology information of the stacking system to the slave control board after the slave control board is inserted. This invention is applicable for collecting the topology information of a stacking system comprising distributed dual control board devices.

Abstract: Executing an accelerator application program in a hybrid computing environment with a host computer having a host computer architecture; an accelerator having an accelerator architecture, the accelerator architecture optimized, with respect to the host computer architecture, for speed of execution of a particular class of computing functions; the host computer and the accelerator adapted to one another for data communications by a system level message passing module, where executing an accelerator application program on an accelerator includes receiving, from a host application program on the host computer, operating information for an accelerator application program; designating a directory as a CWD for the accelerator application program, separate from any other CWDs of any other applications running on the accelerator; assigning, to the CWD, a name that is unique with respect to names of other CWDs of other applications in the computing environment; and starting the accelerator application program on the a

Abstract: Disclosed herein are lattice reduction systems and methods for a MIMO communication system. One such method includes providing a channel matrix corresponding to a channel in a MIMO communication system, preprocessing the channel matrix to form at least an upper triangular matrix, implementing a relaxed size reduction process, and implementing a basis update process. Implementing the relaxed size reduction process comprises choosing a first relaxed size reduction parameter for a first-off-diagonal element of the upper triangular matrix, choosing a second relaxed size reduction parameter, which is greater than the first relaxed size reduction parameter, for a second-off-diagonal element of the upper triangular matrix evaluating whether a first relaxed size reduction condition is satisfied for the first-off-diagonal element of the upper triangular matrix, and evaluating whether a second relaxed size reduction condition is satisfied for the second-off-diagonal element of the upper triangular matrix.

Abstract: A system and method for process synchronization in a multi-core computer system. A separate non-caching memory enables a method to synchronize processes executing on multiple processor cores. Since only a very small amount (a few number of bytes), is needed for the synchronization, it is possible to extend the method for inter-processor core message passing by allocating dedicated address space of the on-chip memory for each processor with exclusive write access. Each of the multiple processor cores maintains a dedicated cache while maintaining coherency with the non-cache shared memory.

Abstract: A Multi-Level Processor 200 for reducing the cost of synchronization overhead including an upper level processor 201 for taking control and issuing the right to use shared data and to enter critical sections directly to each of a plurality of lower level processors 202, 203 . . . 20n at processor speed. In one embodiment the instruction registers of lower level parallel processors are mapped to the data memory of upper level processor 201. Another embodiment 1300 incorporates three levels of processors. The method includes mapping the instructions of lower level processors into the memory of an upper level processor and controlling the operation of lower level processors. A variant of the method and apparatus facilitates the execution of Single Instruction Multiple Data (SIMD) and single to multiple instruction and multiple data (SI>MIMD). The processor includes the ability to stretch the clock frequency to reduce power consumption.

Abstract: Provided are a computer program product, system, and method for determining processor offsets to synchronize processor time values. A determination is made of a master processor offset from one of a plurality of time values of the master processor and a time value of one of the slave processors. A determination is made of slave processor offsets, wherein each slave processor offset is determined from the master processor offset, one of the time values of the master processor, and a time value of the slave processor. A current time value of the master processor is adjusted by the master processor offset. A current time value of each of the slave processors is adjusted by the slave processor offset for the slave processor whose time value is being adjusted.

Abstract: A distributed processing system is described that employs “application-based” specialization. In particular, the distributed processing system is constructed as a collection of computing nodes in which each computing node performs a particular processing role within the operation of the overall distributed processing system. Each of the computing nodes includes an operating system, such as the Linux operating system, and includes a plug-in software module to provide a distributed memory operating system that employs the role-based computing techniques. An administration node maintains a database that defines a plurality of application roles. Each role is associated with a software application, and specifies a set of software components necessary for execution of the software application. The administration node deploys the software components to the application nodes in accordance with the application roles associates with each of the application nodes.

Abstract: Data processing in a hybrid computing environment that includes a host computer having a host computer architecture; an accelerator having an accelerator architecture, the accelerator architecture optimized, with respect to the host computer architecture, for speed of execution of a particular class of computing functions; the host computer and the accelerator adapted to one another for data communications by a system level message passing module; and a host application process executing on the host computer. Data processing such a hybrid computing environment includes starting, at the behest of the host application process, a thread of execution on the accelerator; returning, by the system level message passing module to the host application process, a process identifier (‘PID’) for the thread of execution; and managing, by the host application process, the thread of execution on the accelerator as though the thread of execution were a thread of execution on the host computer.

Abstract: A semiconductor memory device for use in a multiprocessor system includes a shared memory area and a reset signal generator. The shared memory area is accessible by the processors of the multiprocessor system through different ports, and is assigned to a portion of a memory cell array. The reset signal generator is configured to provide a reset enable signal to a processor, predetermined as a slave processor among the multiple processors, for a predetermined time after an initial booting of the multiprocessor system. The reset signal generator also provides a reset disable signal to the slave processor after the predetermined time lapses.

Abstract: In a semiconductor LSI that sequentially performs predetermined processing on data input successively, a host CPU, a plurality of sequencers, and a data engine are connected in a hierarchical manner with the host CPU at top and the data engine at bottom. Each sequencer includes a memory that stores a parameter for execution of the sequencer, a memory controller, a loop counter, a sequence controller, and an interface unit that handles transmission and reception of signals with an external unit of the sequencer. The interface units of the plurality of sequencers have the same specifications.

Abstract: A wireless communication system hosts a plurality of processes in accordance with a communication protocol. The system includes application specific instruction set processors (ASISPs) that provided computation support for the process. Each ASISP is capable of executing a subset of the functions of a communication protocol. A scheduler is used to schedule the ASISPs in a time-sliced algorithm so that each ASISP supports several processes. In this architecture, the ASISP actively performs computations for one of the supported processes (active process) at any given time. The state information of each process supported by a particular ASISP is stored in a memory bank that is uniquely associated with the ASISP. When a scheduler instructs an ASISP to change which process is the active process, the state information for the inactivated process is stored in the memory bank and the state information for the newly activated process is retrieved from the memory bank.

Abstract: A hardware engine control apparatus includes: a plurality of hardware engines (HWEs) connected by a control bus, each of the hardware engines executing a series of different kinds of processing; a host control device that outputs control commands for controlling operation of the HWEs to a subordinate control device; and the subordinate control device that has a register, in which the control commands from the host control device is sequentially set, and outputs the control commands set in the register to the control bus at timing based on a clock signal. The HWEs operate according to the control commands output from the subordinate control device.

Abstract: Embodiments of the present invention facilitate dynamically adapting to state information changes in a graphics processing environment. In one embodiment, a master register holds state information corresponding to units of work (threads) to be performed. The state information in the master register is copied to a per-group state register when a group of threads is to be launched. The per-group state register is coupled to processing engines configured to process the threads, so that the processing engines read state information from the per-group state register rather than the master register. In another embodiment, a number of master registers may be used to store state information for different types of threads.

Abstract: A distributed architecture and method for maintaining the integrity of data streams within a multi-pipelined processing environment. The architecture comprising a communications network for carrying a plurality of data streams and a master processor adapted to process one or more messages in at least one of the data streams, the message processing including the creation of one or more data packets within the stream, each packet encapsulating at least a transaction summary of the data that has been processed. The architecture further comprising at least one slave processor per master processor adapted to emulate the transactional state of the master processor by regenerating the data stream as a result of processing the one or more data packets, whereupon in response to an error event on the master processor, the slave processor acts to avoid interrupting the data stream by generating one or more successive data packet(s).

Abstract: A register circuit having a plurality of registers enabling the writing and reading of data by the specification of an address; a register controlling circuit monitoring data of a plurality of registers of the register circuit through the specification of an address, and writing, to a register pre-established in the register circuit, for activating devices; and a signal transmitting circuit causing a device to execute a specific operation, based on a specified address and on data read from the register circuit are provided; and not only is a collection of first bits for controlling jointly the individual operations of the plurality of devices assigned in a first register that is established in advance in the plurality of registers, but also second bits for controlling individually the individual operations in the plurality of devices are assigned respectively in a plurality of respective second registers that differ from the first register.

Abstract: A digital signal processor uses a number of independent sub-processors that may be controlled by a master programmable controller. For example, a specialized input processor may process input signals while a specialized output processor may process output signals. Each of these processors may also accomplish math functions when input and output processing is not necessary. The various processors may communicate with one another through general purpose registers which receive data and provide data to any of the processors in the system. Math processors may be added as needed to accomplish desired mathematical functions. In addition, a RAM processor may be utilized to hold the results of intermediate calculations in one embodiment of the present invention. In this way, an adaptable and scaleable design may be implemented that accommodates a variety of different operations without requiring redesign of all the components.

Abstract: Embodiments relate to systems and methods for reading from and writing to interface peripherals or other shared resources during robust computation utilizing temporally separated redundant execution. Embodiments can be utilized in safety-relevant applications related to automotive, banking and finance, aerospace, defense, Internet payment, and others.

Abstract: Executing a service program for an accelerator application program in a hybrid computing environment that includes a host computer and an accelerator, the host computer and the accelerator adapted to one another for data communications by a system level message passing module; where the service program includes a host portion and an accelerator portion and executing a service program for an accelerator includes receiving, from the host portion, operating information for the accelerator portion; starting the accelerator portion on the accelerator; providing, to the accelerator portion, operating information for the accelerator application program; establishing direct data communications between the host portion and the accelerator portion; and, responsive to an instruction communicated directly from the host portion, executing the accelerator application program.

Abstract: An apparatus, method, and system for synchronicity independent, resource delegating, power and instruction optimizing processor is provided where instructions are delegated between various processing resources of the processor. An Integer Processing Unit (IPU) of the processor delegates complicated mathematical instructions to a Mathematical Processing Unit (MPU) of the processor. Furthermore, the processor puts underutilized processing resources to sleep thereby increasing power usage efficiency. A cache of the processor is also capable of accepting delegated operations from the IPU. As such, the cache performs various logical operations on delegated requests allowing it to lock and share memory without requiring extra processing cycles by the entire processor.

Abstract: A safety master configured to communicate with a plurality of safety slaves over a safety field network or with a plurality of safety local I/O units connected by a safety back plane bus of the safety master, wherein each of the plurality of safety slaves and safety local I/O units allow connection to safety I/O devices in a plurality of cell equipment, and wherein the safety master receives a status signal indicating a “safe state” or an “unsafe state” related to cell equipment from each of the corresponding plurality of safety slaves or safety local I/O units, and controls operation/stop of cell equipment by executing an interlock operation program with the received status signal as an input to output an operation instruction signal.

Abstract: An apparatus and method provide power to perform functions on a computing device. In one example, the apparatus contains multiple processors that may operate at different power levels to consume different amounts of power. Also, any of the multiple processors may perform different functions. For example, one processor may be a low power processor that may control or operate at least one peripheral device to perform a low capacity function. Control may also switch from the low power processor to a high capacity processor. In one example, the high capacity processor controls the low power processor and further controls the at least one peripheral device through the lower power processor.

Abstract: Contention in a distributed processor computer system with a replicated message environment is reduced. The system comprises processor consumers intercommunicating via a server interface that receives a message from a producer. The server favors one consumer, marks the message accordingly, communicates the marked message to the system, and delays the processing in another consumer beyond a predetermined time, for example the time normally taken to process a message.

Abstract: Methods, systems, and machine-readable media are disclosed for passing executable instructions via synchronized data objects. According to one embodiment, passing executable instructions from a first device to a second device during a synchronization operation between the first device and the second device can comprise synchronizing one or more data objects between the first device and the second device. At least one of the one or more data objects can include one or more executable instructions from the first device. The one or more executable instructions can be read from the data objects on the second device. Each of the one or more executable instructions may then be executed on the second device.

Abstract: The present application is directed towards systems and methods for coordination and management of a shared resource in a multi-core system. In a multi-core system, multiple cores may be utilizing a shared resource. However, internal resources common to the shared resource may need to be initialized by only one core, and independent and uncoordinated initialization by multiple cores may cause errors. The present invention provides systems and methods for coordinating such initialization and use through a handshaking protocol.

Abstract: A digital signal processor uses a number of independent sub-processors that may be controlled by a master programmable controller. For example, a specialized input processor may process input signals while a specialized output processor may process output signals. Each of these processors may also accomplish math functions when input and output processing is not necessary. The various processors may communicate with one another through general purpose registers which receive data and provide data to any of the processors in the system. Math processors may be added as needed to accomplish desired mathematical functions. In addition, a RAM processor may be utilized to hold the results of intermediate calculations in one embodiment of the present invention. In this way, an adaptable and scaleable design may be implemented that accommodates a variety of different operations without requiring redesign of all the components.

Abstract: A hybrid computer system is provided, including first and second computer devices. The first computer device is configured with the second computer device via a connection unit. Each of the first computer device and the second computer device is capable of operating independently when the first computer device and the second computer device are separated. The first computer device and the second computer device communicate with each other in a master-slave structure and combined with each other into a single system. The peripheral devices of the first and second computer devices are shared, wherein the first and second computer devices are master/slave systems or slave/master systems.

Abstract: The systems and methods may include receiving an initial population of parent chromosome data structures, where each parent chromosome data structure provides a plurality of genes; selecting pairs of parent chromosome data structures; applying at least one evolutionary operator to the genes of the selected pairs to generate a plurality of child chromosome data structures; allocating, the generated plurality of child chromosome structures to a plurality slave processors, where each slave processor evaluates one or more of the plurality of child chromosome data structures and generates respective objective function values; receiving objective function values for a portion of the plurality of allocated child chromosome data structures; merging the parent chromosome data structures with the received portion of the child chromosome data structures for which objective function values have been received; and identifying a portion of the merged set of chromosome data structures as an elite set of chromosome data stru

Abstract: A network device may comprise an auxiliary processor to conserve the power of the network device. The auxiliary processor may modify one or more definition parameters of the programmable processing unit based on determining that the load value of the programmable processing unit is lower than a threshold value. The modifying of the definition parameters may comprise reducing an operating frequency of the programmable processing unit, reducing a number of a micro-programmable units resident on the programmable processing unit, or both.

Abstract: One embodiment of a video processor includes a first media processing device coupled to a first memory and a second media processing device coupled to a second memory. The second media processing device is coupled to the first media processing device via a scalable bus. A software driver configures the media processing devices to provide video processing functionality. The scalable bus carries video data processed by the second media processing device to the first media processing device where the data is combined with video data processed by the first media processing device to produce a processed video frame. The first media processing device transmits the combined video data to a display device. Each media processing device is configured to process separate portions of the video data, thereby enabling the video processor to process video data more quickly than a single-GPU video processor.

Abstract: A packet data communication on-chip interconnect system is provided including a network interface efficiently controlling a transaction performed between at least one master intellectual property (IP) block and at least one slave IP block connected via a Network on a Chip (NoC). According to an aspect of the present invention, traffic functioning and throughput of the entire NoC may be improved by appropriately controlling an operation of performing a lock operation according to an Advance eXtensible Interface (AXI) protocol in the network interface of the packet data communication on-chip interconnect system.